Classification of urban environments using feature extraction and random forest

Anjos, Camila Souza dos; Lacerda, M. G.; Andrade, Leidiane do Livramento; Salles, Roberto Neves

doi:10.1109/igarss.2017.8127174

Cited by 14 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, the segmentation process is divided into two steps: firstly, the Multi-resolution Segmentation (MRS) algorithm is used; and then we use the Spectral Difference Segmentation (SDS) algorithm. Those techniques yielded good results in other works (Anjos et al, 2017b).…”

Section: Methodssupporting

confidence: 52%

Impact of Segmentation Parameters on the Classification of VHR Images Acquired by Rpas

Lacerda¹,

Shiguemori²,

Damião³

et al. 2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. RPAs (Remotely Piloted Aircrafts) have been used in many Remote Sensing applications, featuring high-quality imaging sensors. In some situations, the images are interpreted in an automated fashion using object-oriented classification. In this case, the first step is segmentation. However, the setting of segmentation parameters such as scale, shape, and compactness may yield too many different segmentations, thus it is necessary to understand the influence of those parameters on the final output. This paper compares 24 segmentation parameter sets by taking into account classification scores. The results indicate that the segmentation parameters exert influence on both classification accuracy and processing time.

show abstract

Section: Methodssupporting

confidence: 52%

Impact of Segmentation Parameters on the Classification of VHR Images Acquired by Rpas

Lacerda¹,

Shiguemori²,

Damião³

et al. 2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Taking into consideration the results from other scientific papers (Anjos et al, 2017b), we proceed to the segmentation of the orthophoto mosaic (item 2.2) in two steps. The first step is the Multi-resolution Segmentation (MRS), whose parameters are: Scale = 50; Shape = 0.1; and Compactness = 0.5.…”

Section: Methodsmentioning

confidence: 99%

Analysis of VHR Image Classification by Single and Ensemble of Classifiers

Lacerda

Shiguemori

Damião

et al. 2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Given the wide variety of image classifiers available nowadays, some questions remain about the accuracy and processing time of Very High Resolution (VHR) images. Another question concerns the use of a Single or Ensemble Classifiers. Of course, the main factor to consider is the quality of the classified image, but computational cost is also important, especially in applications that require real-time processing. Given this scenario, this paper aims to relate the accuracy of seven single classifiers and the ensemble of the same classifiers with the processing time. In this paper the ensemble of classifiers had the best results in terms of accuracy, however, it comes to processing time, the decision tree had the best performance.

show abstract

“…The So2Sat LCZ42 data set has been used for LCZ classification in several cities (Feng et al, 2019;Jing et al, 2019;Qiu et al, 2018cQiu et al, , 2020cTaubenböck et al, 2020;Yang et al, 2019b (Yokoya et al, 2018). The top four teams used a variety of classification algorithms deriving from computer vision and machine learning (dos Anjos et al, 2017;Sukhanov et al, 2017;Xu et al, 2017a;Yokoya et al, 2017). Bechtel et al (2019) suggested that the use of robust generalized classification algorithms and the incorporation of multi-source data can improve the transferability of LCZ samples.…”

Section: Lcz Samplesmentioning

confidence: 99%

“…For example,Wei & Blaschke (2016) used the multi-resolution segmentation and self-organization map (SOM) algorithms to classify LCZs. dosAnjos et al (2017) used the multiresolution segmentation and random forest (RF) algorithms for LCZ classification Simanjuntak et al (2019). used the multiresolution segmentation algorithm that includes two segmentation levels to classify LCZs.Instead of using high-resolution remote sensing data,Collins & Dronova (2019) explored the potential of object-based LCZ classification using medium-resolution Landsat data.…”

mentioning

confidence: 99%